Are there any benchmarks for SIL?
zhihaocheng opened this issue · 2 comments
zhihaocheng commented
Hi @kengz , your SLM-Lab is a great job. I am trying to use SIL (self-imitation learning) for my project. Do you have tested this algorithm in SLM-Lab, especially for PPO? I tried to implement SIL with PPO, but I found it did not work. In other words, SIL does not help to improve PPO.
kengz commented
@zhihaocheng SIL is not part of the main benchmark we ran with Atari. But there are some sanity-check basic benchmark of SIL in SLM Lab:
zhihaocheng commented
@kengz many thanks